We present a feature extraction method that evaluates the audio quality of push-button sounds based on wavelet transforms. Using a continuous wavelet transform, push-button sounds are represented in the time-frequency plane. For each sound, features identifying sound characteristics in terms of sound pressure and reverberation are compactly represented with triangular biorthogonal wavelets. These wavelets belong to a two-dimensional nonseparable set of functions that enable a multiscale signal representation. Together with an auditory impression of the sounds extracted by the semantical differential method, a preliminary experiment is then performed to evaluate automated recognition of push-button sounds using wavelet analysis.

Authors: Fujinoki, Kensuke; Murakoshi, Kodai; Ishimitsu, Shunsuke
Affiliations: Hiroshima City University, Hiroshima, Japan; Oshima National College of Maritime Technology, Yamaguchi, Japan(See document for exact affiliation information.)
AES Conference: 45th International Conference: Applications of Time-Frequency Processing in Audio (March 2012)
Paper Number: 2-1
Publication Date: March 1, 2012 Import into BibTeX
Subject: Representation of Audio
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=16177

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD 45thPapers)   /conf/45/aes45-000019.pdf

Start a discussion about this paper!